Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    U.S. state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -making
    -0.07
    making
    -0.07
     그러나
    -0.06
    Andrew
    -0.06
     caching
    -0.06
    二
    -0.06
     Cloud
    -0.06
    project
    -0.06
    じゃ
    -0.06
    rejected
    -0.06
    POSITIVE LOGITS
    .พ
    0.07
     LF
    0.07
    CriticalSection
    0.07
    _disp
    0.07
     ابن
    0.06
    	IN
    0.06
     проход
    0.06
    .Ref
    0.06
     personalized
    0.06
    .Pos
    0.06
    Act Density 0.009%

    No Known Activations